# Joint Learning of Neural Networks via Iterative Reweighted Least Squares

Source: [Joint Learning of Neural Networks via Iterative Reweighted Least Squares](<https://www.sota2.com/research/paper/68fa65e11e209131cea0d1e8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:38:30.146Z

Authors: Zaiwei Zhang, Xiangru Huang, Qixing Huang, Xiao Zhang, Yuan Li

Published: 2019-05-16T04:38:55.000Z

## Abstract

In this paper, we introduce the problem of jointly learning feed-forward neural networks across a set of relevant but diverse datasets. Compared to learning a separate network from each dataset in isolation, joint learning enables us to extract correlated information across multiple datasets to significantly improve the quality of learned networks. We formulate this problem as joint learning of multiple copies of the same network architecture and enforce the network weights to be shared across these networks. Instead of hand-encoding the shared network layers, we solve an optimization problem to automatically determine how layers should be shared between each pair of datasets. Experimental results show that our approach outperforms baselines without joint learning and those using pretraining-and-fine-tuning. We show the effectiveness of our approach on three tasks: image classification, learning auto-encoders, and image generation.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1905.06526>)

[PDF](<https://arxiv.org/pdf/1905.06526.pdf>)